{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:30:33Z","timestamp":1784399433985,"version":"3.55.0"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200731","type":"print"},{"value":"9783031200748","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20074-8_9","type":"book-chapter","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:23:11Z","timestamp":1668198191000},"page":"146-162","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":243,"title":["A-OKVQA: A Benchmark for\u00a0Visual Question Answering Using World Knowledge"],"prefix":"10.1007","author":[{"given":"Dustin","family":"Schwenk","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Apoorv","family":"Khandelwal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Clark","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenneth","family":"Marino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roozbeh","family":"Mottaghi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,12]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"9_CR3","unstructured":"Banerjee, S., Lavie, A.: METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In: ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization (2005)"},{"key":"9_CR4","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Chang, Y., Narang, M.B., Suzuki, H., Cao, G., Gao, J., Bisk, Y.: WebQA: multihop and multimodal QA. arXiv (2021)","DOI":"10.1109\/CVPR52688.2022.01600"},{"key":"9_CR6","unstructured":"Chen, X., et al.: Microsoft COCO captions: data collection and evaluation server. arXiv (2015)"},{"key":"9_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"9_CR8","unstructured":"Gao, H., Mao, J., Zhou, J., Huang, Z., Wang, L., Xu, W.: Are you talking to a machine? dataset and methods for multilingual image question. In: NeurIPS (2015)"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Garc\u00eda, N., Otani, M., Chu, C., Nakashima, Y.: KnowIT VQA: answering knowledge-based questions about videos. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6713"},{"key":"9_CR10","doi-asserted-by":"publisher","first-page":"3618","DOI":"10.1073\/pnas.1422953112","volume":"112","author":"D Geman","year":"2015","unstructured":"Geman, D., Geman, S., Hallonquist, N., Younes, L.: Visual turing test for computer vision systems. Proc. Natl. Acad. Sci. 112, 3618\u20133623 (2015)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"9_CR14","unstructured":"HuggingFace: https:\/\/huggingface.co\/sentence-transformers\/multi-qa-MiniLM-L6-cos-v1"},{"key":"9_CR15","unstructured":"HuggingFace: https:\/\/huggingface.co\/sentence-transformers\/nli-bert-base"},{"key":"9_CR16","unstructured":"HuggingFace: https:\/\/huggingface.co\/sentence-transformers\/average_word_embeddings_glove.6B.300d"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Hussain, Z., et al.: Automatic understanding of image and video advertisements. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.123"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Jain, A., Kothyari, M., Kumar, V., Jyothi, P., Ramakrishnan, G., Chakrabarti, S.: Select, substitute, search: a new benchmark for knowledge-augmented visual question answering. In: SIGIR (2021)","DOI":"10.1145\/3404835.3463259"},{"key":"9_CR19","unstructured":"Jiang, Y., Natarajan, V., Chen, X., Rohrbach, M., Batra, D., Parikh, D.: Pythia v0.1: the winning entry to the VQA challenge 2018. arXiv (2018)"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Kamath, A., Clark, C., Gupta, T., Kolve, E., Hoiem, D., Kembhavi, A.: Webly supervised concept expansion for general purpose vision models. arXiv (2022)","DOI":"10.1007\/978-3-031-20059-5_38"},{"key":"9_CR22","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual Genome: connecting language and vision using crowdsourced dense image annotations. IJCV 123, 32\u201373 (2017)","journal-title":"IJCV"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Li, Q., Fu, J., Yu, D., Mei, T., Luo, J.: Tell-and-answer: towards explainable visual question answering using attributes and captions. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1164"},{"key":"9_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"9_CR25","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d","volume":"22","author":"H Liu","year":"2004","unstructured":"Liu, H., Singh, P.: ConceptNet-a practical commonsense reasoning tool-kit. BT Technol. J. 22, 211\u2013226 (2004)","journal-title":"BT Technol. J."},{"key":"9_CR26","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized bert pretraining approach. arXiv (2019)"},{"key":"9_CR27","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: VilBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: NeurIPS (2019)"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Lu, J., Goswami, V., Rohrbach, M., Parikh, D., Lee, S.: 12-in-1: Multi-task vision and language representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"9_CR29","unstructured":"Malinowski, M., Fritz, M.: A multi-world approach to question answering about real-world scenes based on uncertain input. In: NeurIPS (2014)"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Marino, K., Chen, X., Parikh, D., Gupta, A.K., Rohrbach, M.: KRISP: integrating implicit and symbolic knowledge for open-domain knowledge-based VQA. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01389"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: OK-VQA: a visual question answering benchmark requiring external knowledge. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"9_CR32","unstructured":"Mokady, R., Hertz, A., Bermano, A.H.: ClipCap: CLIP prefix for image captioning. arXiv (2021)"},{"key":"9_CR33","doi-asserted-by":"crossref","unstructured":"Park, D.H., et al.: Multimodal explanations: justifying decisions and pointing to the evidence. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00915"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Post, M.: A call for clarity in reporting BLEU scores. In: Conference on Machine Translation (2018)","DOI":"10.18653\/v1\/W18-6319"},{"key":"9_CR36","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"9_CR37","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI blog (2019)"},{"key":"9_CR38","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR 21, 1\u201367 (2020)","journal-title":"JMLR"},{"key":"9_CR39","unstructured":"Ren, M., Kiros, J., Zemel, R.S.: Exploring models and data for image question answering. In: NeurIPS (2015)"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Shah, S., Mishra, A., Yadati, N., Talukdar, P.P.: KVQA: knowledge-aware visual question answering. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: ACL (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"9_CR42","unstructured":"Singh, A., et al.: MMF: a multimodal framework for vision and language research (2020). https:\/\/github.com\/facebookresearch\/mmf"},{"key":"9_CR43","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"Tan, H.H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. In: EMNLP (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"9_CR45","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Zhu, Y., Stiefelhagen, R., Torralba, A., Urtasun, R., Fidler, S.: MovieQA: understanding stories in movies through question-answering. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.501"},{"key":"9_CR46","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, Q., Shen, C., Dick, A.R., van den Hengel, A.: Explicit knowledge-based reasoning for visual question answering. In: IJCAI (2017)","DOI":"10.24963\/ijcai.2017\/179"},{"key":"9_CR47","doi-asserted-by":"publisher","first-page":"2413","DOI":"10.1109\/TPAMI.2017.2754246","volume":"40","author":"P Wang","year":"2017","unstructured":"Wang, P., Wu, Q., Shen, C., van den Hengel, A., Dick, A.R.: FVQA: fact-based visual question answering. TPAMI 40, 2413\u20132427 (2017)","journal-title":"TPAMI"},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"West, P., et al.: Symbolic knowledge distillation: from general language models to commonsense models. arXiv preprint arXiv:2110.07178 (2021)","DOI":"10.18653\/v1\/2022.naacl-main.341"},{"key":"9_CR49","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: An empirical study of GPT-3 for few-shot knowledge-based VQA. arXiv (2021)","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"9_CR50","unstructured":"Yi, K., Wu, J., Gan, C., Torralba, A., Kohli, P., Tenenbaum, J.B.: Neural-symbolic VQA: disentangling reasoning from vision and language understanding. In: NeurIPS (2018)"},{"key":"9_CR51","doi-asserted-by":"crossref","unstructured":"Yu, L., Park, E., Berg, A.C., Berg, T.L.: Visual madlibs: fill in the blank description generation and question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.283"},{"key":"9_CR52","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00688"},{"key":"9_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: VinVL: revisiting visual representations in vision-language models. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"9_CR54","doi-asserted-by":"crossref","unstructured":"Zhu, X., Anguelov, D., Ramanan, D.: Capturing long-tail distributions of object subcategories. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.122"},{"key":"9_CR55","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Groth, O., Bernstein, M.S., Fei-Fei, L.: Visual7W: grounded question answering in images. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.540"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20074-8_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:26:39Z","timestamp":1668198399000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20074-8_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200731","9783031200748"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20074-8_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"12 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}